© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58121
    Prev
    Next
    INDEX
    Explanations

    plans and proposals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _DECL
    -0.08
    ç§ijæĬĢè¿ĽæŃ¥
    -0.08
    åį³å°Ĩ
    -0.08
    oe
    -0.08
     Ends
    -0.08
    åѤåĦ¿
    -0.08
    ç«ĭ项
    -0.07
    åħ³
    -0.07
    æİĽ
    -0.07
    lect
    -0.07
    POSITIVE LOGITS
    建议
    0.20
    æıIJè®®
    0.18
    建èŃ°
    0.17
     proposals
    0.16
     suggestions
    0.15
    æıIJåĩº
    0.15
    æıIJæ¡Ī
    0.15
    åĢ¡è®®
    0.15
    æıIJåĩºäºĨ
    0.15
    æıIJåĩºçļĦ
    0.15
    Activations Density 0.057%

    No Known Activations